CN110334870B - Photovoltaic power station short-term power prediction method based on gated cyclic unit network - Google Patents

Photovoltaic power station short-term power prediction method based on gated cyclic unit network Download PDF

Info

Publication number
CN110334870B
CN110334870B CN201910613978.8A CN201910613978A CN110334870B CN 110334870 B CN110334870 B CN 110334870B CN 201910613978 A CN201910613978 A CN 201910613978A CN 110334870 B CN110334870 B CN 110334870B
Authority
CN
China
Prior art keywords
predicted
value
network
power
day
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910613978.8A
Other languages
Chinese (zh)
Other versions
CN110334870A (en
Inventor
陈志聪
陈辉煌
吴丽君
程树英
林培杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fuzhou University
Original Assignee
Fuzhou University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fuzhou University filed Critical Fuzhou University
Priority to CN201910613978.8A priority Critical patent/CN110334870B/en
Publication of CN110334870A publication Critical patent/CN110334870A/en
Application granted granted Critical
Publication of CN110334870B publication Critical patent/CN110334870B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Quality & Reliability (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Photovoltaic Devices (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention relates to a photovoltaic power station short-term power prediction method based on a gated cyclic unit network. The method comprises the following steps: the method comprises the following steps: step S1: selecting meteorological parameters as model input according to weather types of days to be predicted, wherein the dominant meteorological parameters are different in different weather types; step S2: processing 20 days of history data before the day to be predicted, eliminating abnormal values and values of the night, and then performing normalization processing on the historical power and the historical NWP meteorological parameters to serve as a training data set; step S3: learning the training data set by adopting a gate control cycle unit network, and adjusting parameters of the network by using a root-mean-square back propagation algorithm; step S4: and taking the NWP meteorological parameters of the day to be predicted as the input of the model to obtain the predicted power value. The method can obviously improve the accuracy and reliability of the short-term power prediction of the photovoltaic power station.

Description

Photovoltaic power station short-term power prediction method based on gated cyclic unit network
Technical Field
The invention belongs to a short-term prediction technology of photovoltaic power station power, and particularly relates to a short-term power prediction method of a photovoltaic power station based on a gated cyclic unit network.
Background
Solar energy has the characteristics of cleanness, no pollution, wide source, inexhaustibility and the like, has potential and is widely concerned by various countries, but the defects begin to appear along with the increase of the proportion of solar power generation in a power grid, and the solar energy has the characteristics of large weather influence, large fluctuation and strong randomness, which is not beneficial to the stability of the power grid, and the safety problem exists because the fluctuation of the power grid exceeds a certain limit. By using the short-term power prediction method of the photovoltaic power station, the photovoltaic capacity can be estimated in advance, and a basis is provided for a power grid manager to allocate a power grid and reduce the influence of solar energy fluctuation on the power grid.
At present, relevant research at home and abroad mainly focuses on ultra-short term and short term power prediction of a single power station, and the reason is that most of electric energy to be generated can be traded within 1 day in the future from the beginning of prediction. According to different power prediction principles and methods, the power prediction method can be divided into three categories: physical methods, statistical methods, and hybrid methods. The physical method mainly utilizes a physical formula to carry out reasoning calculation, and the method has complex modeling, a plurality of factors needing to be considered and lower prediction precision; the statistical method needs a large amount of historical power generation data and sometimes corresponding meteorological data, generally speaking, an artificial neural network is used for learning the historical data, a mapping relation between environmental factors and output power or between historical power and future power is established, and then the power of a predicted day can be obtained; the mixing method combines physical and statistical methods or different statistical methods to build a more complex model, generally with higher accuracy.
A general neural network (such as a BP network) only considers the influence of the current input meteorological parameters on the photovoltaic power, a cyclic neural network not only considers the influence of the current input meteorological parameters on the photovoltaic power, but also considers the influence of historical power on the current power, the prediction accuracy can be effectively improved, and a gated cyclic unit network is one of the cyclic neural networks and can better capture the dependence relationship with larger time step distance in a time sequence compared with the general cyclic neural network.
At present, no research for using the gated-cycle cell network for predicting the output power of the photovoltaic power plant is found in publicly published documents and patents.
Disclosure of Invention
The invention aims to provide a photovoltaic power station short-term power prediction method based on a gated cyclic unit network, which overcomes the defects of the prior art, so that the accuracy of photovoltaic power station short-term power prediction is improved.
In order to achieve the purpose, the technical scheme of the invention is as follows: a photovoltaic power station short-term power prediction method based on a gated cyclic unit network comprises the following steps,
s1, selecting meteorological parameters as model input according to weather types of days to be predicted, wherein the meteorological parameters are different in dominant positions in different weather types;
step S2, processing N-day calendar history data before the day to be predicted, eliminating abnormal values and values of the night, and then performing normalization processing on the historical power and the historical NWP meteorological parameters to serve as a training data set;
step S3, learning the training data set by adopting a gate control cycle unit network, and adjusting the parameters of the network by using a root-mean-square back propagation algorithm;
and step S4, taking the NWP meteorological parameters of the day to be predicted as the input of the model, and obtaining the predicted power value.
In an embodiment of the present invention, in the step S1, the weather parameters corresponding to the weather types are divided into: ground level irradiance, scattering level irradiance, and ambient temperature; partial cloudy day: ground level irradiance, scattering level irradiance, ambient temperature, and relative humidity; in cloudy days: ground level irradiance, scattering level irradiance, ambient temperature, and relative humidity; in rainy days: relative humidity.
In an embodiment of the present invention, in step S2, the abnormal value is removed, that is, the data corresponding to the part of the power variation caused by the non-meteorological parameter is removed; and eliminating the value of the night, namely eliminating the data of the night, taking the data from day 6 to 19, and then normalizing the data to the interval [0,1 ].
In an embodiment of the present invention, the step S3 is implemented as follows,
step S31, forward propagation, using a gated cyclic unit network, whose formula is:
Ut＝sigmoid(WU1Xt+WU2Ht-1+BU)
Rt＝sigmoid(WR1Xt+WR2Ht-1+BR)
Figure BDA0002123273750000021
wherein, XtIs the input to the gated cyclic unit network at time t; htThe hidden state value at the time t is the gated cycle unit network output; u shapetTo update the gate output; rtIs the reset gate output;
Figure BDA0002123273750000022
is in a transient state; wU1、WU2、WR1、WR2、WH～1And
Figure BDA0002123273750000023
is the weight; b isU、BRAnd
Figure BDA0002123273750000024
is a bias value;
step S32, back propagation, wherein a root-mean-square back propagation algorithm is used, and the method comprises the following steps:
first, an objective function is defined:
Figure BDA0002123273750000025
wherein, p is a parameter to be adjusted, namely a weight value and a bias value;
Figure BDA0002123273750000026
is an objective function; y istThe actual power value at the time t; a is at(p) is a network output value at the time t, namely a predicted value; e.g. of the typet(p) is the corresponding error;
then, parameters are adjusted using a root-mean-square back propagation algorithm:
Figure BDA0002123273750000031
Figure BDA0002123273750000032
wherein alpha is the learning rate and the expression is
Figure BDA0002123273750000033
St,dpIs a similar momentum term; β is a hyperparameter between 0 and 1; epsilon is a small quantity that avoids the presence of a denominator of zero, and takes the value of 10-8。
Compared with the prior art, the invention has the following beneficial effects: according to the method, the current meteorological parameters are considered by the gating cycle unit network, meanwhile, the influence of historical power on the current power is also considered, and through verification and analysis of examples, results show that compared with the existing photovoltaic power station short-term power prediction method, the accuracy and reliability of photovoltaic power station short-term power prediction are greatly improved.
Drawings
FIG. 1 is a flow chart of a photovoltaic power plant short-term power prediction method based on a gated cyclic unit network in the invention.
FIG. 2 is a block diagram of a gated loop cell network in accordance with the present invention.
FIG. 3 is a schematic diagram of a descending curve of the root-mean-square back-propagation algorithm of the present invention.
Fig. 4 is a diagram of a prediction result of a photovoltaic power plant short-term power prediction model based on a gated cyclic unit network in a sunny day in an embodiment of the present invention.
FIG. 5 is a graph of the prediction results of the short-term power prediction model of the photovoltaic power plant based on the gated cyclic unit network in part cloudy days according to an embodiment of the present invention.
Fig. 6 is a diagram of the prediction results of the photovoltaic power plant short-term power prediction model based on the gated cyclic unit network in cloudy days according to an embodiment of the present invention.
Fig. 7 is a diagram of a prediction result of a photovoltaic power plant short-term power prediction model based on a gated cyclic unit network in a rainy day in an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is specifically explained below with reference to the accompanying drawings.
As shown in fig. 1, the invention provides a photovoltaic power plant short-term power prediction method based on a gated cyclic unit network, which comprises the following steps,
step S1, selecting meteorological parameters as model input according to weather types of days to be predicted, wherein the dominant meteorological parameters are different in different weather types;
step S2, processing N (20 in the example) ephemeris history data before the day to be predicted, eliminating abnormal values and values of the night, and then carrying out normalization processing on the historical power and the historical NWP meteorological parameters to be used as a training data set;
step S3, learning the training data set by adopting a gate control cycle unit network, and adjusting the parameters of the network by using a root-mean-square back propagation algorithm;
and step S4, taking the NWP meteorological parameters of the day to be predicted as the input of the model, and obtaining the predicted power value.
In step S1, the weather parameters corresponding to the weather type are divided into: ground level irradiance, scattering level irradiance, and ambient temperature; partial cloudy day: ground level irradiance, scattering level irradiance, ambient temperature, and relative humidity; in cloudy days: ground level irradiance, scattering level irradiance, ambient temperature, and relative humidity; in rainy days: relative humidity.
In step S2, removing abnormal values, that is, removing data corresponding to the power variation caused by non-meteorological parameters (e.g., system fault and human factor); and eliminating the value of the night, namely eliminating the data of the night, taking the data from day 6 to 19, and then normalizing the data to the interval [0,1 ].
The specific implementation steps of step S3 are as follows,
step S31, forward propagation, using a gated round-robin unit network (GRU network), whose formula is:
Ut＝sigmoid(WU1Xt+WU2Ht-1+BU)
Rt＝sigmoid(WR1Xt+WR2Ht-1+BR)
Figure BDA0002123273750000041
wherein, XtIs the input to the gated-cycle cell network at time t; htThe hidden state value at the time t is the gated cycle unit network output; u shapetTo update the gate output; rtIs the reset gate output;
Figure BDA0002123273750000042
is in a transient state; wU1、WU2、WR1、WR2、
Figure BDA0002123273750000043
And
Figure BDA0002123273750000044
is the weight; b isU、BRAnd
Figure BDA0002123273750000045
is a bias value; the structure of the gated loop cell network is shown in FIG. 2;
step S32, back propagation, wherein a root-mean-square back propagation algorithm is used, and the method comprises the following steps:
first, an objective function is defined:
Figure BDA0002123273750000046
wherein, p is a parameter to be adjusted, namely a weight value and a bias value;
Figure BDA0002123273750000047
is an objective function; y istThe actual power value at the time t; a ist(p) is a network output value at the time t, namely a predicted value; e.g. of the typet(p) is the corresponding error;
then, the parameters are adjusted using a root-mean-square back propagation algorithm:
Figure BDA0002123273750000048
Figure BDA0002123273750000051
wherein alpha is the learning rate and the expression is
Figure BDA0002123273750000052
St,dpIs a similar momentum term; beta is a hyperparameter between 0 and 1; epsilon is a small quantity that avoids the presence of a denominator of zero, and takes the value of 10-8. A schematic diagram of the falling curve of the root-mean-square back propagation algorithm is shown in fig. 3.
Preferably, in this example, a photovoltaic power prediction is performed under four different weather conditions, namely, clear weather, partly cloudy weather, cloudy weather and rainy weather, with a photovoltaic power station No. 22 (with a capacity of 16.8kW) of a DKA Solar center (server sunlight Solar center), and test data of each weather type are selected as follows: 2018/6/20, 2018/6/21, 2018/6/22; partial cloudy day: 2018/4/19, 2018/4/20, 2018/4/21; in cloudy days: 2017/3/7, 2017/3/8, 2017/3/9; in rainy days: 2018/3/8, 2018/3/9, 2018/11/7; the training data was selected as the 20-day history data prior to the test data. The predicted effect maps are shown in fig. 4 to 7. As can be seen from the Mean Absolute Percent Error (MAPE) and the Root Mean Square Error (RMSE) in Table 1, the method provided by the invention can perform more accurate prediction, and fully embodies the accuracy of the invention.
TABLE 1 Performance testing under four weather conditions
Figure BDA0002123273750000053
The above are preferred embodiments of the present invention, and all changes made according to the technical scheme of the present invention that produce functional effects do not exceed the scope of the technical scheme of the present invention belong to the protection scope of the present invention.

Claims (3)

1. A photovoltaic power station short-term power prediction method based on a gated cyclic unit network is characterized by comprising the following steps,
step S1, selecting meteorological parameters as model input according to weather types of days to be predicted, wherein the dominant meteorological parameters are different in different weather types;
step S2, processing N-day calendar history data before the day to be predicted, eliminating abnormal values and values of the night, and then performing normalization processing on the historical power and the historical NWP meteorological parameters to serve as a training data set;
step S3, learning the training data set by adopting a gate control cycle unit network, and adjusting the parameters of the network by using a root-mean-square back propagation algorithm;
step S4, taking the NWP meteorological parameters of the day to be predicted as the input of a model to obtain a predicted power value;
the specific implementation steps of step S3 are as follows,
step S31, forward propagation, using a gated cyclic unit network, whose formula is:
Ut＝sigmoid(WU1Xt+WU2Ht-1+BU)
Rt＝sigmoid(WR1Xt+WR2Ht-1+BR)
Figure FDA0003577043880000011
wherein, XtIs the input to the gated-cycle cell network at time t; htThe hidden state value at the time t is the gated cycle unit network output; u shapetTo update the gate output; rtIs the reset gate output;
Figure FDA0003577043880000019
is in a transient state; wU1、WU2、WR1、WR2、
Figure FDA0003577043880000012
And
Figure FDA0003577043880000013
is the weight; b isU、BRAnd
Figure FDA0003577043880000014
is a bias value;
step S32, back propagation, using a root mean square back propagation algorithm, in the following manner:
first, an objective function is defined:
Figure FDA0003577043880000015
wherein, p is a parameter to be adjusted, namely a weight and an offset value;
Figure FDA0003577043880000016
is an objective function; y istThe actual power value at the time t; a ist(p) is a network output value at the time t, namely a predicted value; e.g. of a cylindert(p) is the corresponding error;
then, parameters were adjusted using the root mean square back propagation algorithm:
Figure FDA0003577043880000017
Figure FDA0003577043880000018
wherein alpha istFor the learning rate, the expression is
Figure FDA0003577043880000021
St,dpIs a similar momentum term; β is a hyperparameter between 0 and 1; epsilon is a small quantity that avoids the presence of a denominator of zero, and takes the value of 10-8。
2. The method for predicting the short-term power of the photovoltaic power plant based on the gated-cyclic cell network as claimed in claim 1, wherein the weather parameters corresponding to the weather type in the step S1 comprise: ground horizontal irradiance, scattering horizontal irradiance and ambient temperature corresponding to sunny days; ground level irradiance, scattering level irradiance, ambient temperature and relative humidity corresponding to a portion of an overcast day or an overcast day; relative humidity in rainy weather.
3. The photovoltaic power plant short-term power prediction method based on the gated cyclic unit network as claimed in claim 1, wherein in step S2, abnormal values, that is, data corresponding to power changes caused by non-meteorological parameters, are removed; and eliminating the value of the night, namely eliminating the data of the night, taking the data from day 6 to 19, and normalizing the data to the interval [0,1 ].
CN201910613978.8A 2019-07-09 2019-07-09 Photovoltaic power station short-term power prediction method based on gated cyclic unit network Active CN110334870B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910613978.8A CN110334870B (en) 2019-07-09 2019-07-09 Photovoltaic power station short-term power prediction method based on gated cyclic unit network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910613978.8A CN110334870B (en) 2019-07-09 2019-07-09 Photovoltaic power station short-term power prediction method based on gated cyclic unit network

Publications (2)

Publication Number Publication Date
CN110334870A CN110334870A (en) 2019-10-15
CN110334870B true CN110334870B (en) 2022-05-31

Family

ID=68144440

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910613978.8A Active CN110334870B (en) 2019-07-09 2019-07-09 Photovoltaic power station short-term power prediction method based on gated cyclic unit network

Country Status (1)

Country Link
CN (1) CN110334870B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112115648B (en) * 2020-09-23 2023-12-01 贵州电网有限责任公司 Transformer top layer oil temperature prediction method based on improved deep learning method
CN112149905A (en) * 2020-09-25 2020-12-29 福州大学 Photovoltaic power station short-term power prediction method based on wavelet transformation and wavelet neural network
CN112990553B (en) * 2021-02-23 2023-11-14 中国电建集团华东勘测设计研究院有限公司 Wind power ultra-short-term power prediction method using self-attention mechanism and bilinear fusion
CN112926653B (en) * 2021-02-25 2022-08-26 山东大学 Photovoltaic power short-term prediction method and system based on small-scale weather type correction
CN113779860B (en) * 2021-03-01 2024-05-28 北京科益虹源光电技术有限公司 Excimer laser energy model identification method and device
CN113919232A (en) * 2021-10-25 2022-01-11 北京航天创智科技有限公司 Photovoltaic power station power prediction method and system based on recurrent neural network

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106651007A (en) * 2016-11-24 2017-05-10 北京理工大学 Method and device for GRU-based medium and long-term prediction of irradiance of photovoltaic power station
CN108448610A (en) * 2018-03-12 2018-08-24 华南理工大学 A kind of short-term wind power prediction method based on deep learning
CN109711609A (en) * 2018-12-15 2019-05-03 福州大学 Photovoltaic plant output power predicting method based on wavelet transformation and extreme learning machine
CN109799533A (en) * 2018-12-28 2019-05-24 中国石油化工股份有限公司 A kind of method for predicting reservoir based on bidirectional circulating neural network

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106557828A (en) * 2015-09-30 2017-04-05 中国电力科学研究院 A kind of long time scale photovoltaic is exerted oneself time series modeling method and apparatus

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106651007A (en) * 2016-11-24 2017-05-10 北京理工大学 Method and device for GRU-based medium and long-term prediction of irradiance of photovoltaic power station
CN108448610A (en) * 2018-03-12 2018-08-24 华南理工大学 A kind of short-term wind power prediction method based on deep learning
CN109711609A (en) * 2018-12-15 2019-05-03 福州大学 Photovoltaic plant output power predicting method based on wavelet transformation and extreme learning machine
CN109799533A (en) * 2018-12-28 2019-05-24 中国石油化工股份有限公司 A kind of method for predicting reservoir based on bidirectional circulating neural network

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
RMSProp and equilibrated adaptive learning rates for non-convex optimization;Yann N. Dauphin et al.;《IEICE Transactions on Fundamentals of Electronics》;20151231;全文 *
基于深度门控循环单元神经网络的短期风功率预测模型;牛哲文等;《电力自动化设备》;20180504(第05期);全文 *
计及天气类型指数的光伏发电短期出力预测;袁晓玲等;《中国电机工程学报》;20131205(第34期);全文 *
采用Seq2Seq模型的非受限词义消歧方法;唐善成等;《西北大学学报(自然科学版)》;20190604(第03期);全文 *

Also Published As

Publication number Publication date
CN110334870A (en) 2019-10-15

Similar Documents

Publication Publication Date Title
CN110334870B (en) Photovoltaic power station short-term power prediction method based on gated cyclic unit network
CN111008728B (en) Prediction method for short-term output of distributed photovoltaic power generation system
CN109002915B (en) Photovoltaic power station short-term power prediction method based on Kmeans-GRA-Elman model
CN109086928B (en) Photovoltaic power station real-time power prediction method based on SAGA-FCM-LSSVM model
CN106532778B (en) Method for calculating maximum access capacity of distributed photovoltaic grid connection
CN109685257A (en) A kind of photovoltaic power generation power prediction method based on Support vector regression
CN109858673A (en) A kind of photovoltaic generating system power forecasting method
CN113496311A (en) Photovoltaic power station generated power prediction method and system
CN110766134A (en) Photovoltaic power station short-term power prediction method based on cyclic neural network
CN112733462A (en) Ultra-short-term wind power plant power prediction method combining meteorological factors
CN110880789A (en) Economic dispatching method for wind power and photovoltaic combined power generation system
CN110443405A (en) A kind of built photovoltaic power station power generation amount forecasting system and method
CN105260800A (en) Photovoltaic module temperature prediction method and device
CN114004139A (en) Photovoltaic power generation power prediction method
CN112149905A (en) Photovoltaic power station short-term power prediction method based on wavelet transformation and wavelet neural network
Meng et al. A new PV generation power prediction model based on GA-BP neural network with artificial classification of history day
CN115021331A (en) Clean energy-based ground water wind-solar integrated compensation method based on contribution coefficient method
CN105741192B (en) Short-term wind speed combined forecasting method for wind turbine engine room of wind power plant
CN109767353A (en) A kind of photovoltaic power generation power prediction method based on probability-distribution function
CN111242371B (en) Photovoltaic power generation short-term prediction correction method based on non-iterative multi-model
Sahoo et al. Energy forecasting for grid connected MW range solar PV system
Xu et al. Influence of different optimization aalgorithms on prediction accuracy of photovoltaic output power based on BP neural network
CN110796292A (en) Photovoltaic power short-term prediction method considering haze influence
CN113036806B (en) Wind-solar complementary system capacity proportioning method based on random programming model
Xiao et al. A statistical photovoltaic power forecast model (spf) based on historical power and weather data

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant